INDEX

Explanations

terms associated with company reputation and public perception

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ględ

-0.46

findpost

-0.44

 désolés

-0.42

 beat

-0.41

IUrlHelper

-0.40

awaiter

-0.40

HomeAsUpEnabled

-0.39

SneakyThrows

-0.39

lored

-0.39

 practice

-0.39

POSITIVE LOGITS

 reputation

0.96

 reputations

0.85

 réputation

0.83

 reputación

0.79

Reputation

0.75

 Reputation

0.75

 reputa

0.73

 perception

0.69

 Wahrnehmung

0.69

 perceptions

0.67

Activations Density 0.347%

terms associated with company reputation and public perception

No Comments

No Known Activations